该模型使用了超过400张高质量的原始图片进行训练。
训练图片主要来自藤岛康介的原画集,还有一部分来自动画版原画师:松原秀典。
推荐权重:0.6~1.0
推荐CFG:5~6
推荐模型:Animagine XL V3
--- --- --- --- --- --- --- ---
The model used more than 400 high-quality original pictures for training.
The training pictures are mainly from the original painting collection of Kosuke Fujishima, and some are from the original artist of the animation version: Hidenoria Matsubara.
Recommendation Weight:0.6~1.0
Recommendation CFG:5~6
Recommendation Model:Animagine XL V3